Dear AuntMinnie Member,
The composition of breast tissue -- whether it's dense or fatty, for example -- can have a major impact on efforts to predict a woman's risk of developing cancer, and on detecting tumors when they develop. A pair of articles we're featuring this week in our Women's Imaging Digital Community examines recent efforts to analyze and define breast tissue morphology.
In the first article, staff writer Shalmali Pal investigates two studies that examine changes in breast density over time. In the first study, researchers from Massachusetts General Hospital in Boston tracked women over a period of eight to 14 years to see how their breast density changed over time.
Another study, by researchers in the U.K., examined how the consumption of isoflavones might impact breast density. Isoflavones are a compound found in soy-based food products, and interest in the substance is rising due to its potential health benefits. However, isoflavones also can act as weak estrogens, and the group wanted to find out if the substance had an impact on breast density, as estrogen does.
Another story we're highlighting, by staff writer Erik L. Ridley, examines how the menstrual cycle can affect breast vascularity -- and in turn the ability to use ultrasound to evaluate breast lesions.
Read both articles in our Women's Imaging Digital Community, at womens.auntminnie.com.


![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)







![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)







